INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Isa
    -0.09
    .emp
    -0.07
    xs
    -0.07
    engine
    -0.07
     Ratio
    -0.07
    ENCIL
    -0.07
    ALI
    -0.07
     Abe
    -0.07
    ordinate
    -0.06
     множе
    -0.06
    POSITIVE LOGITS
     phot
    0.16
     Phot
    0.12
    phot
    0.10
    Phot
    0.10
     '..
    0.07
    0.07
     \
    0.07
     Hit
    0.07
    Foot
    0.06
    ../../
    0.06
    Act Density 0.005%

    No Known Activations